模型40
GPT-6.2 Astra 与 Sol 编码智能体指数表现
原标题:GPT-6.2 Astra is flat with GPT-6 Astra, and GPT-6.2 Sol loses 3 points relative to GPT-6.1 Sol in the Artificial Analysis Coding Agent In...
在 Artificial Analysis 编码智能体指数中(Codex harness 以最大 effort 运行),GPT-6.2 Astra 与 GPT-6 Astra 持平,而 GPT-6.2 Sol 相对 GPT-6.1 Sol 下降 3 分。对 Sol 而言,这一下降由 SWE-Atlas-QnA-AA 上 14 分的下滑所致——在该项上,该模型比其前代更可能在回答中遗漏关键事实。
中文译文尚未完成,先为你展示原文。
GPT-6.2 Astra is flat with GPT-6 Astra, and GPT-6.2 Sol loses 3 points relative to GPT-6.1 Sol in the Artificial Analysis Coding Agent Index (Codex harness at max effort). For Sol, the drop is driven by a 14-point drop in SWE-Atlas-QnA-AA, where the model is more likely than its predecessor to omit key facts in its responses.
同一件事的其他报道2 篇
Artificial Analysis 评测 GPT-6.2 Astra 与 Sol:智能指数第二,编码未见提升
Artificial Analysis · 原文
Artificial Analysis 编码智能体指数:GPT-6.2 表现持平或下滑
Artificial Analysis · 原文
